Hyperspectral aerospace imagery spectral bands optimal selection in solving remote sensing thematic tasks

1Stankevich, SA
1State institution «Scientific Centre for Aerospace Research of the Earth of the Institute of Geological Sciences of the National Academy of Sciences of Ukraine», Kyiv, Ukraine
Kosm. nauka tehnol. 2007, 13 ;(2):025-028
Publication Language: Russian
We offer an approach to hyperspectral aerospace imagery optimal spectral bands selection on the basis of informativity criterion which includes remote sensing objects spectra separability as the Kullback-Leibler divergence, the equivalent spatial resolution of the given spectral bands combination for given remote sensing objects and the equivalent signal-to-noise ratio during the detection of remote sensing objects by their multidimensional optical signals. The logic of hyperspectral aerospace imagery optimal spectral bands selection in solving remote sensing thematic tasks on the basis of pseudogradient search of possible combinations of spectral bands in space is specified. We present quantitative results of multi- and hyperspectral aerospace imagery optimal spectral bands selection in solving some thematic tasks of the remote sensing.
Keywords: aerospace imagery, remote sensing, spectra separability
1. Alekseev O. G. Complex application of discrete optimization methods, 278 p. (Nauka, Moscow, 1987) [in Russian].
2. Lyalko V. I., Popov M. O. (Eds) Multispectral remote sensing in nature management, 360 p. (Nauk.dumka, Kyiv, 2006) [in Ukrainian].
3. Glebov N. I., Kochetov Yu. A., Plyasunov A. V. Optimization methods, 74 p. (NSU, Novosibirsk, 2003) [in Russian].
4. Kononov V. I., Stankevich S. A. Digital Aerospace Images with High and Low Resolution Informativity Comparative Evaluation. Scientific Notes of Taurida National V.I. Vernadsky University, 17 (2), 88—95 (2004) [in Russian].
5. Stankevich S. A. The quantitative evaluation of the informativity of hyperspectral aerospace imagery on the solution of remote-sensing thematic tasks. Reports of the National Academy of Sciences of Ukraine, No. 10, 136—139 (2006) [in Ukrainian].
6. Stankevich S. A. Probabilistic-frequency evaluation of equivalent spatial resolution for multispectral aerospace images. Kosm. nauka tehnol., 12 (2-3), 79—82 (2006) [in Ukrainian].
7. Stankevich S. A. Evaluation of optical transfer functions and restoring digital aerospace images by inverse filtering. Probl. Upravl. Inform., No. 3, 116—123 (2006) [in Russian].
https://doi.org/10.1615/J Automat Inf Scien.v38.i6.40 
8. Jones D. R. A taxonomy of global optimization methods based on response surfaces. J. Global Optimization, 21, 345—383 (2001).
9. Landgrebe D. A. Signal theory methods in multispectral remote sensing, 512 p. (John Wiley, Hoboken, 2003).
10. Aarts E. H. L., Lenstra J. K. (Eds) Local search in combinatorial optimization, 512 p. (John Wiley, Chichester, 1997).
11. Neumaier A. complete search in continuous global optimization and constraint satisfaction. Acta Numerica, Ed. by A. Iserles, 1—99 (Univ. Press, Cambridge, 2004).

12. Nocedal J., Wright S. J. Numerical optimization, 656 p. (Springer Verlag, Berlin, 1999).